* Use sparse vector storage fixture without RocksDB
* Fix some tests
* Replace RocksDB sparse storage with Gristore in mutable text index tests
* Use in-memory vector storage in multivector HNSW test
* Flag many more RocksDB specifics in tests
* Use database placeholder type without RocksDB flag
* Flag more tests
* Flag even more tests
* Fix imports, fix typo, and repair base test build
* Initialize dummy database if RocksDB flag is disabled
* Assert correct storage types
* Don't use old vector storage type when RocksDB is disabled
* Expos default for vector storage type only in tests
* Only expose simple segment constructor in tests
* Don't derive Default
* Fix inverted appendable flag
* Bump Rust edition to 2024
* gen is a reserved keyword now
* Remove ref mut on references
* Mark extern C as unsafe
* Wrap unsafe function bodies in unsafe block
* Geo hash implements Copy, don't reference but pass by value instead
* Replace secluded self import with parent
* Update execute_cluster_read_operation with new match semantics
* Fix lifetime issue
* Replace map_or with is_none_or
* set_var is unsafe now
* Reformat
* bump and migrate to rand 0.9.0
also bump rand_distr to 0.5.0 to match it
* Migrate AVX2 and SSE implementations
* Remove unused thread_rng placeholders
* More random migrations
* Migrate GPU tests
* bump seed
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
* Measure read io for payload storage
* Add Hardware Counter to update functions
* Fix tests and benches
* Rename (some) *_measured functions back to original
* implement mmap sparse vector storage
* add to VectorStorageEnum
* clippy
* add tests, fix both simple and mmap storages
* smol correction on total_vector_count
* add sparse storage type to config
* fix reading config without storage type
* generate openapi
* use blob_store by path
* hidden setting to enable new storage
* validate existing path in `BlobStore::open()`
* use new dir for each sparse vector name
* fix and rename `max_point_offset`
Plus some extra refactors
* add storage compat test, to always check both storages work
* fix opening of storage + other misc fixes
* FIX!!!
`Unset` operations in the Tracker weren't updating the
`next_pointer_id`. So, when reopening the storage, those points wouldn't
get marked as deleted in the bitslice, thus creating the illusion that
they should exist, when they did not.
* refactor naming from `iter_*` to `for_each_*`
* fix checking for BlobStore existance
* fix typo
* fix error message
* better docs for open_or_create
* fix after rebase
* Add CPU measurement for multivectors
* add further test sparse vector search
* make updating vector_query_context consistent
* review fix + take element type into consideration
---------
Co-authored-by: generall <andrey@vasnetsov.com>
* Add HardwareCounterCell and counting for sparse plain search
* Add measurement for indexed sparse vector
* add tests for calculations
* move SegmentQueryContent higher in the call stack
* move hardware counters inside the query context
* fix clippy
* Fix applying hardware measurements and add test for this
---------
Co-authored-by: generall <andrey@vasnetsov.com>
* Move build_index out of VectorIndex
* Build index in HNSWIndex::open()
* Introduce HnswIndexOpenArgs
* Proper deletion
* Improve tests
* HNSW::open(): add warn, comment and assert
* Revert to making up the config if it does not exist
* Rename InvertedIndex* -> InvertedIndexCompressed*
* Extract method VectorIndexEnum::fill_idf_statistics
* Extend VectorIndexEnum with new variants
* Introduce sparse::InvertedIndex::Version
* Replace SparseVectorIndexVersion -> InvertedIndex::Version
* Introduce sparse_vector_index::OpenArgs
* SparseVectorIndex::open: do not build index if directory is empty
Otherwise it would build the index twice since `SegmentBuilder::build()`
calls `::open()`, then `::build_index()`. This restores the old (<=v1.9)
behavior.
* Renames
* add `query` to shard trait
* add missing conversions for query
* update grpc docs
* Query response has intermediate results
* add ShardQueryResponse description
* move pub use to the top, keep only one way of reaching reexports
* introduce QueryContext, which accumulates runtime info needed for executing search
* fmt
* propagate query context into segment internals
* [WIP] prepare idf stats for search query context
* Split SparseVector and RemmapedSparseVector to guarantee we will not mix them up on the type level
* implement filling of the query context with IDF statistics
* implement re-weighting of the sparse query with idf
* fmt
* update idf param only if explicitly specified (more consistent with diff param update
* replace idf bool with modifier enum, improve further extensibility
* test and fixes
* Update lib/collection/src/operations/types.rs
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
* review fixes
* fmt
---------
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
* byte storage with quantization
raw scorer integration
config and test
are you happy fmt
fn renamings
cow refactor
use quantization branch
quantization update
* are you happy clippy
* don't use distance in quantized scorers
* fix build
* add fn quantization_preprocess
* apply preprocessing for only cosine float metric
* fix sparse vectors tests
* update openapi
* more complicated integration test
* update openapi comment
* mmap byte storages support
* fix async test
* move .unwrap closer to the actual check of the vector presence
* fmt
* remove distance similarity function
* avoid copying data while working with cow
---------
Co-authored-by: generall <andrey@vasnetsov.com>
* move check for unindexed segment size inside the segment to allow proxy shard decide where to search better
* fmt
* move indexed_only check inside the plain index
* Multivec knob for SegmentConfig
* regen openapi
* add TODO for next step
* introduce multivecconfig to support more similarity aggregation
* update openapi
* Move CPU count function to common, fix wrong CPU count in visited list
* Change default number of rayon threads to 8
* Use CPU budget and CPU permits for optimizer tasks to limit utilization
* Respect configured thread limits, use new sane defaults in config
* Fix spelling issues
* Fix test compilation error
* Improve breaking if there is no CPU budget
* Block optimizations until CPU budget, fix potentially getting stuck
Our optimization worker now blocks until CPU budget is available to
perform the task.
Fix potential issue where optimization worker could get stuck. This
would happen if no optimization task is started because there's no
available CPU budget. This ensures the worker is woken up again to
retry.
* Utilize n-1 CPUs with optimization tasks
* Better handle situations where CPU budget is drained
* Dynamically scale rayon CPU count based on CPU size
* Fix incorrect default for max_indexing_threads conversion
* Respect max_indexing_threads for collection
* Make max_indexing_threads optional, use none to set no limit
* Update property documentation and comments
* Property max_optimization_threads is per shard, not per collection
* If we reached shard optimization limit, skip further checks
* Add remaining TODOs
* Fix spelling mistake
* Align gRPC comment blocks
* Fix compilation errors since last rebase
* Make tests aware of CPU budget
* Use new CPU budget calculation function everywhere
* Make CPU budget configurable in settings, move static budget to common
* Do not use static CPU budget, instance it and pass it through
* Update CPU budget description
* Move heuristic into defaults
* Fix spelling issues
* Move cpu_budget property to a better place
* Move some things around
* Minor review improvements
* Use range match statement for CPU count heuristics
* Systems with 1 or 2 CPUs do not keep cores unallocated by default
* Fix compilation errors since last rebase
* Update lib/segment/src/types.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
* Update lib/storage/src/content_manager/toc/transfer.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
* Rename cpu_budget to optimizer_cpu_budget
* Update OpenAPI specification
* Require at least half of the desired CPUs for optimizers
This prevents running optimizations with just one CPU, which could be
very slow.
* Don't use wildcard in CPU heuristic match statements
* Rename cpu_budget setting to optimizer_cpu_budget
* Update CPU budget comments
* Spell acquire correctly
* Change if-else into match
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
* Rename max_rayon_threads to num_rayon_threads, add explanation
* Explain limit in update handler
* Remove numbers for automatic selection of indexing threads
* Inline max_workers variable
* Remove CPU budget from ShardTransferConsensus trait, it is in collection
* small allow(dead_code) => cfg(test)
* Remove now obsolete lazy_static
* Fix incorrect CPU calculation in CPU saturation test
* Make waiting for CPU budget async, don't block current thread
* Prevent deadlock on optimizer signal channel
Do not block the optimization worker task anymore to wait for CPU budget
to be available. That prevents our optimizer signal channel from being
drained, blocking incoming updates because the cannot send another
optimizer signal. Now, prevent blocking this task all together and
retrigger the optimizers separately when CPU budget is available again.
* Fix incorrect CPU calculation in optimization cancel test
* Rename CPU budget wait function to notify
* Detach API changes from CPU saturation internals
This allows us to merge into a patch version of Qdrant. We can
reintroduce the API changes in the upcoming minor release to make all of
it fully functional.
---------
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
Co-authored-by: Luis Cossío <luis.cossio@outlook.com>
* sparse vectors with large indices support
* fix unit tests
* add tracker file to snapshot
* fix unit tests
* are you happy clippy
* fix config loading
* test with max value
* fix python tests
* fix consensus tests
* review remarks; acc test for inverted index
* sparse vectors query scorer
plain search test without internals
fix sparse_vector_index_plain_search
fix async scorer build
fix unit tests
are you happy fmt
sparse index with full query support
fix benches, use exact flag to force plain search
add alias and comment to exact flag
fix tests
recommendations TODOs fix
add simple test
add todo
refactor index
test vs comparison dense and sparse discovery
are you happy fmt
propogate error from avg negatives
reuse filtered points list
rollback api changes
better discovery test
are you happy fmt
rollback openapi
fix build
fix tests
review remark recommendations
review remarks
review remarks
codespell
integrate plain search
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
fix comment of plain search
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
fix tests
* simplify search query function
